A New Genre Classification with the Colors of Music

The aim of this study is to bring a new perspective for the classification of the songs, revealing of the colors of music. The first effort is to transform songs into images. The colorful images have been attained with Short time Fourier transform, discrete cosine transform and time to spatial transformation and some extra processing. It has been observed that the images of different music genres obtained with the same method have different colors. But some of them have similar colors and patterns, which making difficult to classify. Pre-trained deep convolutional network have been trained with these images. For five Turkish musical genres, nearly up to 60% classification accuracy has been achieved and for ten musical genre of a benchmark musical dataset nearly up to 54% classification accuracy has been achieved. In future studies, it has been planned to create the images using timbral texture and rhythmic contents, for increasing the accuracy.

Müzik Türlerinin Derin Öğrenme Ağları ile Sınıflandırılması

Bu çalışmada günümüzde görüntülerin sınıflandırılmasında yüksek başarı sağlayan derin öğrenme ağları ile müzik türlerinin sınıflandırılması hedeflenmiştir. Bu çalışmanın amacı, müziklerin renklerini ortaya çıkararak şarkıların sınıflandırılması için yeni bir bakış açısı getirmektir. Bu amaçla ilk olarak, müzik türlerinden seçilen parçalar görüntülere dönüştürülmüştür. Renkli görüntüler kısa zaman fourier dönüşümü, ayrık kosinüs dönüşümü ve uzamsal dönüşüm yöntemleri ve bazı önişlemlerle elde edilmiştir. Farklı türlere ait görüntülerin renklerinin farklı olduğu görülmüştür. Ancak bazı türlerde sınıflandırmayı zorlaştıracak benzer renkler ve desenler görülmüştür. Önceden eğitilmiş derin konvolüsyon ağı bu görüntülerle eğitilmiştir. Türkçe müziklerden seçilen, arabesk, pop, türk halk müziği, türk sanat müziği ve rock müzikleri ile eğitilen ağda, yaklaşık % 60'a kadar bir sınıflandırma doğruluğu elde edilmiş ve yine literatürde müzik türü sınıflandırılmasında kullanılan genel bir veri tabanı ile yapılan testlerde, on farklı müzik türü için yaklaşık% 54’e kadar bir sınıflandırma doğruluğu elde edilmiştir.

PDF

___

[1] M. Kobayakawa, M. Hoshi and K. Yuzawa, "Music Genre Classification of MPEG AAC Audio Data," 2014 IEEE International Symposium on Multimedia, Taichung, 2014, pp. 347-352. doi: 10.1109/ISM.2014.25

[2] E. Cetinic and S. Grgic, "Genre classification of paintings," 2016 International Symposium ELMAR, Zadar, 2016, pp. 201-204. doi: 10.1109/ELMAR.2016.7731786G.

[3] C. Jebari and M. A. Wani, "A Multi-label and Adaptive Genre Classification of Web Pages," 2012 11th International Conference on Machine Learning and Applications, Boca Raton, FL, 2012, pp. 578-581. doi: 10.1109/ICMLA.2012.106

[4] Karatana and O. Yildiz, "Music genre classification with machine learning techniques," 2017 25th Signal Processing and Communications Applications Conference (SIU), Antalya, 2017, pp. 1- 4.doi: 10.1109/SIU.2017.7960694

[5] G. Tzanetakis and P. Cook, "Musical genre classification of audio signals," in IEEE Transactions on Speech and Audio Processing, vol. 10, no. 5, pp. 293-302, July 2002.

[6] Pachet, Francois & Cazaly, D. “A classification of musical genre” in Proc RIAO Content-Based Multimedia Information Access Conf, Paris, France, March, 2000.

[7] Kyu-Phil Han, Young-Sik Park, Seong-Gyu Jeon, Gwang-Choon Lee and Yeong-Ho Ha, "Genre classification system of TV sound signals based on a spectrogram analysis," in IEEE Transactions on Consumer Electronics, vol. 44, no. 1, pp. 33-42, Feb. 1998.

[8] Ba Tu Truong and C. Dorai, "Automatic genre identification for content-based video categorization," Proceedings 15th International Conference on Pattern Recognition. ICPR-2000, Barcelona, Spain, 2000, pp. 230-233 vol.4.

[9] R. S. Jasinschi and J. Louie, "Automatic TV program genre classification based on audio patterns," Proceedings 27th EUROMICRO Conference. 2001: A Net Odyssey, Warsaw, Poland, 2001, pp. 370-375.

[10] K. Markov and T. Matsui, "Music Genre and Emotion Recognition Using Gaussian Processes," in IEEE Access, vol. 2, pp. 688-697, 2014.

[11] B. Colaiocco and F. Piazza, "A music retrieval system based on the extraction of non trivial recurrent themes and neural classification," Proceedings of the International Joint Conference on Neural Networks, 2003., Portland, OR, 2003, pp. 1110-1115 vol.2.

[12] Changsheng Xu, N. C. Maddage, Xi Shao, Fang Cao and Qi Tian, "Musical genre classification using support vector machines," 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)., Hong Kong, 2003, pp. V-429.

[13] Tao Li and G. Tzanetakis, "Factors in automatic musical genre classification of audio signals," 2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No.03TH8684), New Paltz, NY, USA, 2003, pp. 143-146.

[14] M. M. Panchwagh and V. D. Katkar, "Music genre classification using data mining algorithm," 2016 Conference on Advances in Signal Processing (CASP), Pune, 2016, pp. 49-53. doi: 10.1109/CASP.2016.7746136

[15] C. Kaur and R. Kumar, "Study and analysis of feature based automatic music genre classification using Gaussian mixture model," 2017 International Conference on Inventive Computing and Informatics (ICICI), Coimbatore, 2017, pp. 465-468.

[16] S. Lippens, J. P. Martens and T. De Mulder, "A comparison of human and automatic musical genre classification," 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing, Montreal, Que., 2004, pp. iv-iv. doi: 10.1109/ICASSP.2004.1326806

[17] D. Turnbull and C. Elkan, "Fast recognition of musical genres using RBF networks," in IEEE Transactions on Knowledge and Data Engineering, vol. 17, no. 4, pp. 580-584, April 2005. doi: 10.1109/TKDE.2005.62

[18] F. Pachet and P. Roy, "Exploring Billions of Audio Features," 2007 International Workshop on Content-Based Multimedia Indexing, Bordeaux, 2007, pp. 227-235. doi: 10.1109/CBMI.2007.385416

[19] S. Sharma, P. Fulzele and I. Sreedevi, "Novel hybrid model for music genre classification based on support vector machine," 2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), Penang, 2018, pp. 395-400.

[20] A. R. Rajanna, K. Aryafar, A. Shokoufandeh and R. Ptucha, "Deep Neural Networks: A Case Study for Music Genre Classification," 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), Miami, FL, 2015, pp. 655-660

[21] S. Vishnupriya and K. Meenakshi, "Automatic Music Genre Classification using Convolution Neural Network," 2018 International Conference on Computer Communication and Informatics (ICCCI), Coimbatore, 2018, pp. 1-4.

[22] A. Elbir, H. O. İlhan, G. Serbes and N. Aydın, "Short Time Fourier Transform based music genre classification," 2018 Electric Electronics, Computer Science, Biomedical Engineerings' Meeting (EBBT), Istanbul, 2018, pp. 1-4.

[23] R. Sarkar, N. Biswas and S. Chakraborty, "Music Genre Classification Using Frequency Domain Features," 2018 Fifth International Conference on Emerging Applications of Information Technology (EAIT), Kolkata, 2018, pp. 1-4.

[24] http:// http://marsyas.info/downloads/datasets.html/ Accessed on: November. 28, 2018

[25] Michalis Papakostas, Theodoros Giannakopoulos, Speech-music discrimination using deep visual feature extractors, Expert Systems with Applications, Volume 114, 2018, Pages 334-344, ISSN 0957-4174.

[26] Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012.